© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105105
    Prev
    Next
    INDEX
    Explanations

    ve followed by s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    1.45
    an
    1.44
    a
    1.43
     that
    1.28
    el
    1.24
    nya
    1.18
    ed
    1.14
    skin
    1.13
    n
    1.13
    sl
    1.13
    POSITIVE LOGITS
     suono
    1.14
     шири
    1.05
     ако
    1.02
     кла
    1.01
     санк
    1.00
     аккумуля
    0.99
     ی
    0.99
     தேவையான
    0.99
     circunstancias
    0.98
    ]
    0.98
    Activations Density 0.000%

    No Known Activations